# Llama JavaScript SDK
> Use the OpenAI JavaScript SDK to integrate with Llama via Helicone to log your Llama usage.
import GenerateKey from "/snippets/generate-key.mdx";
import { strings } from "/snippets/strings.mdx";
import LegacyWarning from "/snippets/legacy-provider-warning.mdx";
## {strings.howToIntegrate}
```javascript
HELICONE_API_KEY=
LLAMA_API_KEY=
```
```javascript Llama SDK
import LlamaAPIClient from 'llama-api-client';
const client = new LlamaAPIClient({
apiKey: process.env.LLAMA_API_KEY,
baseURL: "https://llama.helicone.ai/v1",
defaultHeaders: {
"Helicone-Auth": `Bearer ${process.env.HELICONE_API_KEY}`
}
});
const response = await client.chat.completions.create({
model: 'Llama-4-Maverick-17B-128E-Instruct-FP8',
messages: [
{
role: 'user',
content: 'Hello, how are you?'
}
],
max_completion_tokens: 1024,
temperature: 0.7,
});
console.log(response);
```
```javascript OpenAI SDK
import OpenAI from "openai";
const openai = new OpenAI({
apiKey: process.env.LLAMA_API_KEY,
baseURL: "https://llama.helicone.ai/v1",
defaultHeaders: {
"Helicone-Auth": `Bearer ${process.env.HELICONE_API_KEY}`
}
});
const response = await openai.chat.completions.create({
model: "Llama-4-Maverick-17B-128E-Instruct-FP8",
messages: [{ role: "user", content: "Hello, how are you?" }],
max_completion_tokens: 1024,
temperature: 0.7
});
console.log(response);
```
## {strings.relatedGuides}
{strings.chatbotCookbookDescription}
{strings.howToPromptThinkingModelsCookbookDescription}